All skills
aktsmm avatar

/context-to-video

@848fd9b
by yamapanaktsmm/agent-skills26 stars
4

Turn any context (blog URL, pasted article, PR diff, meeting notes, release notes, raw prompt) into a narrated explainer mp4 with slides, subtitles, and optionally a talking-head avatar. Uses a free local stack (Pillow + edge-tts + ffmpeg) with optional SadTalker for the avatar. Use when the user says "動画化", "explainer video", "解説動画作って", "ブログを動画に", "記事を動画化", "PRを動画で説明", "議事録を動画化", "context to video", or wants an mp4 from arbitrary text/source. Output is mp4 + srt under the user's chosen project workspace.

Use this Skill: https://skilld.dev/gh/aktsmm/agent-skills/context-to-video

This session only. Nothing lands on disk.

referencescustomization.md

≈440 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Customization

声 (edge-tts voice)

voice 性別/言語 印象
ja-JP-NanamiNeural 女性・日本語 落ち着き・標準 (既定)
ja-JP-KeitaNeural 男性・日本語 やや低め・解説向き
ja-JP-AoiNeural 女性・日本語 明るめ
ja-JP-DaichiNeural 男性・日本語 若め
en-US-AvaMultilingualNeural 女性・英語/多言語 自然・推奨
en-US-AndrewMultilingualNeural 男性・英語/多言語 落ち着き

全リスト: edge-tts --list-voices

配色変更

scripts/build_video.py 上部の定数を編集:

BG     = (15, 23, 42)    # 背景
ACCENT = (56, 189, 248)  # アクセント (帯・下線・ドット)
TEXT   = (241, 245, 249) # 本文
MUTED  = (148, 163, 184) # 補助テキスト

ブランドカラーで上書きすればOK。

アスペクト比

W, H を変えるだけ:

  • 16:9 横 (既定): 1920, 1080
  • 9:16 縦 (X/Reels): 1080, 1920
  • 1:1 正方形 (Instagram): 1080, 1080

縦版にする場合は bullets を短く (各 20 字以内) しないと折り返し過多になる。

フォント

FONT_B / FONT_R を差し替え。Windows なら:

  • BIZ UDGothic (既定)
  • YuGothB.ttc / YuGothR.ttc (Yu Gothic)
  • meiryob.ttc / meiryo.ttc (Meiryo)

字幕焼き込み

output/final.mp4 に字幕を焼く場合:

ffmpeg -i final.mp4 -vf "subtitles=final.srt:force_style='FontName=BIZ UDGothic,FontSize=22'" -c:a copy final_burned.mp4

BGM ミックス

ffmpeg -i final.mp4 -i bgm.mp3 -filter_complex "[1:a]volume=0.08[bg];[0:a][bg]amix=inputs=2:duration=first" -c:v copy final_bgm.mp4

音量 0.08 前後がナレを潰さない目安。

Source: SKILL.md on GitHub

1 warning1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The skill is functionally safe but possesses a surface for indirect prompt injection because it processes external content (URLs, PR diffs, and notes) using media generation tools without explicit content sanitization.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: MEDIUM · 2 issues

Signed by skilld at 848fd9b. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 18 hours ago.

Activeupdated 3 months ago
argument-hint
入力(URL/テキスト/PR/メモ)、言語(JP/EN)、長さ目安、アバター要否、出力先パス
user-invocable
true
metadata
{
  "author": "yamapan"
}

README badge

README badge for aktsmm/agent-skills/context-to-video